Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.6383. Min Act: -0.1700
Data Index: 5655980 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.6071. Min Act: -0.1700
Data Index: 6070834 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.4196. Min Act: -0.1700
Data Index: 6003372 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2946. Min Act: -0.1700
Data Index: 8510141 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.3258. Min Act: -0.1700
Data Index: 2679552 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2633. Min Act: -0.1700
Data Index: 1695420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2633. Min Act: -0.1700
Data Index: 1289376 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2321. Min Act: -0.1700
Data Index: 8230485 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2321. Min Act: -0.1700
Data Index: 1475946 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2321. Min Act: -0.1700
Data Index: 2836952 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.2321. Min Act: -0.1700
Data Index: 8683529 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1696. Min Act: -0.1700
Data Index: 5087489 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 6722858 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1696. Min Act: -0.1700
Data Index: 8507115 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1696. Min Act: -0.1700
Data Index: 1530570 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 2134926 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 5980316 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 552300 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 2968447 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6383. Min Range: -6.6383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 2599198 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19